Tootfinder

🔧 YAML frontmatter converts directly to CLI flags: model: opus becomes --model opus, mcp-config: ./mcp.json becomes --mcp-config ./mcp.json, dangerously-skip-permissions: true becomes --dangerously-skip-permissions
🔄 Full Unix philosophy support: Pipe data in and out with stdin/stdout, chain agents together like git diff | review.claude .md or plan.claude .md | implement.codex .md, transparent logging shows what runs

This is an important announcement. Google uses it's ecosystem to gain an advantage, "Announcing Model Context Protocol (MCP) support for Google services"
https://cloud.google.com/blog/products/ai-machine-learning/ann…

Announcing official MCP support for Google services | Google Cloud Blog
Google is announcing official MCP support for Google and Google Cloud services for AI agents.

Google releases fully managed, remote MCP servers to help developers connect AI agents to services such as Maps, BigQuery, Compute Engine, and Kubernetes Engine (Rebecca Bellan/TechCrunch)
https://techcrunch.com/2025/12/10/google-is-going-all-in…

Google launches managed MCP servers that let AI agents simply plug into its tools | TechCrunch
Google is rolling out managed MCP servers to make its services “agent-ready by design,” starting with Maps and BigQuery, aiming to simplify messy integrations and help AI agents use real tools.

Model Context Protocol Server for #HomeAssistant
https://www.home-assistant.io/integrations/mcp_server/

It's kinda weird how the Linux Foundation has accepted to become the dumping ground for tech/infrastructure that fall out of some tech hype. First they picked up a lot of Blockchain stuff, now they do AI infra.

Approximate Proximal Operators for Analog Compressed Sensing Using PN-junction Diode
Soma Furusawa, Taisei Kato, Ryo Hayakawa, Kazunori Hayashi
https://arxiv.org/abs/2510.12065 …

Approximate Proximal Operators for Analog Compressed Sensing Using PN-junction Diode
In order to realize analog compressed sensing, the paper considers approximate proximal operators of the $\ell_1$ and minimax concave penalty (MCP) regularization functions. Specifically, we propose to realize the approximate functions by an electric analog circuit using forward voltage-current (V-I) characteristics of the PN-junction diodes. To confirm the validity of the proposed approach, we employ the proposed approximate proximal operators for the $\ell_1$ and MCP regularization functions …

Sure, you can use tons of #MCP to create a "council of experts" or you can use #ai

Glue, a Slack competitor co-founded last year by David Sacks and designed around threads over channels, raised a $20M Series A and says it has refocused on MCP (Dan Primack/Axios)
https://www.axios.com/2025/10/14/glue-workplace-collaboration-slack

Glue raises $20 million to defeat Slack
The startup was cofounded by White House AI czar Davis Sacks.

@… @… I thought that said MCP Level 2 and boy was I about to lose my shit.
Phew.

Replaced article(s) found for cs.MA. https://arxiv.org/list/cs.MA/new
[1/1]:
- Anemoi: A Semi-Centralized Multi-agent System Based on Agent-to-Agent Communication MCP server fr...
Ren, Forder, Zang, Tahir, Georgio, Deb, Carroll, \urcan, Guo

A look at Model Context Protocol and how it went from a passion project made by Anthropic employees to an industry standard shared through the Linux Foundation (Hayden Field/The Verge)
https://www.theverge.com/ai-artificial-int

AI companies want a new internet — and they think they’ve found the key
Anthropic is donating MCP to the Linux Foundation, to be governed under the Agentic AI Foundation, with other members including OpenAI, Google, and Block.

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
Ningyuan Yang, Guanliang Lyu, Mingchen Ma, Yiyi Lu, Yiming Li, Zhihui Gao, Hancheng Ye, Jianyi Zhang, Tingjun Chen, Yiran Chen
https://arxiv.org/abs/2510.01260

IoT-MCP: Bridging LLMs and IoT Systems Through Model Context Protocol
The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing standardized communication between LLMs and physical devices. We propose IoT-MCP, a novel framework that implements MCP through edge-deployed servers to bridge LLMs and IoT ecosystems. To support rigorous evaluation, we introduce IoT-MCP Bench, the first bench…

KI für iOS: MCP für Apple Intelligence im Anflug
Mit dem Model Context Protocol lassen sich KI-Systeme leicht verbinden. Das soll demnächst beim iPhone möglich werden.
https://www.heise.de/ne…

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
Weibo Zhao, Jiahao Liu, Bonan Ruan, Shaofei Li, Zhenkai Liang
https://arxiv.org/abs/2509.24272 https://

When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation
Model Context Protocol (MCP) servers enable AI applications to connect to external systems in a plug-and-play manner, but their rapid proliferation also introduces severe security risks. Unlike mature software ecosystems with rigorous vetting, MCP servers still lack standardized review mechanisms, giving adversaries opportunities to distribute malicious implementations. Despite this pressing risk, the security implications of MCP servers remain underexplored. To address this gap, we present the…

Extending ResourceLink: Patterns for Large Dataset Processing in MCP Applications
Scott Frees
https://arxiv.org/abs/2510.05968 https://arxiv.org/pdf/2510.0…

Extending ResourceLink: Patterns for Large Dataset Processing in MCP Applications
Large language models translate natural language into database queries, yet context window limitations prevent direct deployment in reporting systems where complete datasets exhaust available tokens. The Model Context Protocol specification defines ResourceLink for referencing external resources, but practical patterns for implementing scalable reporting architectures remain undocumented. This paper presents patterns for building LLM-powered reporting systems that decouple query generation from…

EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol
Kanato Masayoshi, Masahiro Hashimoto, Ryoichi Yokoyama, Naoki Toda, Yoshifumi Uwamino, Shogo Fukuda, Ho Namkoong, Masahiro Jinzaki
https://arxiv.org/abs/2509.15957

EHR-MCP: Real-world Evaluation of Clinical Information Retrieval by Large Language Models via Model Context Protocol
Background: Large language models (LLMs) show promise in medicine, but their deployment in hospitals is limited by restricted access to electronic health record (EHR) systems. The Model Context Protocol (MCP) enables integration between LLMs and external tools. Objective: To evaluate whether an LLM connected to an EHR database via MCP can autonomously retrieve clinically relevant information in a real hospital setting. Methods: We developed EHR-MCP, a framework of custom MCP tools integrate…

3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG
Shun-ichiro Hayashi, Daichi Mukunoki, Tetsuya Hoshino, Satoshi Ohshima, Takahiro Katagiri
https://arxiv.org/abs/2510.04536

3Dify: a Framework for Procedural 3D-CG Generation Assisted by LLMs Using MCP and RAG
This paper proposes "3Dify," a procedural 3D computer graphics (3D-CG) generation framework utilizing Large Language Models (LLMs). The framework enables users to generate 3D-CG content solely through natural language instructions. 3Dify is built upon Dify, an open-source platform for AI application development, and incorporates several state-of-the-art LLM-related technologies such as the Model Context Protocol (MCP) and Retrieval-Augmented Generation (RAG). For 3D-CG generation support, 3Dify…

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
Zikang Guo, Benfeng Xu, Chiwei Zhu, Wentao Hong, Xiaorui Wang, Zhendong Mao
https://arxiv.org/abs/2509.09734

MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools
The Model Context Protocol (MCP) is rapidly emerging as a pivotal open standard, designed to enhance agent-tool integration and interoperability, and is positioned to unlock a new era of powerful, interconnected, and genuinely utilitarian agentic AI. However, despite MCP's growing adoption, existing benchmarks often fail to capture real-world agent performance within this new paradigm, leading to a distorted perception of their true operational value and an inability to reliably differentiate p…

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Zhangchen Xu, Adriana Meza Soria, Shawn Tan, Anurag Roy, Ashish Sunil Agrawal, Radha Poovendran, Rameswar Panda
https://arxiv.org/abs/2510.01179

TOUCAN: Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments
Large Language Model (LLM) agents are rapidly emerging as powerful systems for automating tasks across domains. Yet progress in the open-source community is constrained by the lack of high quality permissively licensed tool-agentic training data. Existing datasets are often limited in diversity, realism, and complexity, particularly regarding multi-tool and multi-turn interactions. To address this gap, we introduce Toucan, the largest publicly available tool-agentic dataset to date, containing …

RE: #mcp

Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
Mohammed A. Shehab
https://arxiv.org/abs/2510.02325 https://arxiv.org/pdf/2510…

Agentic-AI Healthcare: Multilingual, Privacy-First Framework with MCP Agents
This paper introduces Agentic-AI Healthcare, a privacy-aware, multilingual, and explainable research prototype developed as a single-investigator project. The system leverages the emerging Model Context Protocol (MCP) to orchestrate multiple intelligent agents for patient interaction, including symptom checking, medication suggestions, and appointment scheduling. The platform integrates a dedicated Privacy and Compliance Layer that applies role-based access control (RBAC), AES-GCM field-level e…

A Measurement Study of Model Context Protocol
Hechuan Guo, Yongle Hao, Yue Zhang, Minghui Xu, Peizhuo Lyu, Jiezhi Chen, Xiuzhen Cheng
https://arxiv.org/abs/2509.25292 https://…

A Measurement Study of Model Context Protocol
The Model Context Protocol (MCP) has been proposed as a unifying standard for connecting large language models (LLMs) with external tools and resources, promising the same role for AI integration that HTTP and USB played for the Web and peripherals. Yet, despite rapid adoption and hype, its trajectory remains uncertain. Are MCP marketplaces truly growing, or merely inflated by placeholders and abandoned prototypes? Are servers secure and privacy-preserving, or do they expose users to systemic r…

Anthropic donates the Model Context Protocol to the Agentic AI Foundation and says there are now more than 10,000 active public MCP servers (Anthropic)
https://www.anthropic.com/news/donating-the-model-context-protocol-and-esta…

Donating the Model Context Protocol and establishing the Agentic AI Foundation
Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
Aueaphum Aueawatthanaphisut
https://arxiv.org/abs/2510.01780 https://arxiv.org/p…

Secure Multi-Modal Data Fusion in Federated Digital Health Systems via MCP
Secure and interoperable integration of heterogeneous medical data remains a grand challenge in digital health. Current federated learning (FL) frameworks offer privacy-preserving model training but lack standardized mechanisms to orchestrate multi-modal data fusion across distributed and resource-constrained environments. This study introduces a novel framework that leverages the Model Context Protocol (MCP) as an interoperability layer for secure, cross-agent communication in multi-modal fede…

Shadow Escape 0-Click Attack in AI Assistants Puts Trillions of Records at Risk
Operant AI reveals Shadow Escape, a zero-click attack using the MCP flaw in ChatGPT, Gemini, and Claude to secretly steal trillions of SSNs and financial data. Traditional security is blind to this new AI threat.
😶‍🌫️ https://

Shadow Escape 0-Click Attack in AI Assistants Puts Trillions of Records at Risk
Follow us on Bluesky, Twitter (X), Mastodon and Facebook at @Hackread

Hi @… - I finally got back to some Claude-coding and told it to build me some BDD tests with Pytest and it seems to have done a reasonable job. https://github.com/adrianco/the-goodi…

Studies of ultrafast dynamics in substrate-free nanoparticles at ELI using Timepix3 optical camera
Dmitrij \v{S}evaev, Andrei Nomerotski, Peter \v{S}vihra, Keshav Sishodia, Andreas Hult Roos, Martin Albrecht, Jakob Andreasson, Maria Krikunova, Eva Klime\v{s}ov\'a
https://arxiv.org/abs/2510.05855

Studies of ultrafast dynamics in substrate-free nanoparticles at ELI using Timepix3 optical camera
We present a novel application of the Timepix3 optical camera (Tpx3Cam) for investigating ultrafast dynamics in substrate-free nanoparticles at the Extreme Light Infrastructure European Research Infrastructure Consortium (ELI ERIC). The camera, integrated into an ion imaging system based on a micro-channel plate (MCP) and a fast P47 scintillator, enables individual time-stamping of incoming ions with nanosecond timing precision and high spatial resolution. The detector successfully captured las…

Ever heard of #graphiti ? #RAG ? 🤖 💽 🔍
Want to use it everywhere, not only on localhost?
Finally, there is a working #MCP for that:
🔗

Ich versuche mich jetzt an einem 4-Gewinnt-MCP-Server.
Wenn Ihnen das nichts sagt, kein Problem.

I case you want to play along, I’ve been experimenting with vector dbs and embedding models for indexing PDFs (white papers) and code.
https://github.com/cwensel/chroma-embedded
This over an mcp with Claude is quite handy.

If the AI was as good as they pretend it is, we wouldn’t need MCP.
It would use the existing human UI.
And if it could be trusted, it wouldn’t output Python—it would generate highly optimized binaries.
…or something closer to that, anyway.
There are some good bits, but also a *lot* of snake oil sales going on here.

A Bayesian model-free dose-finding approach in Phase II clinical trials with the flexibility of historical borrowing
Linxi Han, Qiqi Deng, Feng Yu, Zhangyi He
https://arxiv.org/abs/2509.23777

A Bayesian model-free dose-finding approach in Phase II clinical trials with the flexibility of historical borrowing
Accurate dose selection in Phase II trials is critical to the success of subsequent Phase III trials, but suboptimal choices remain a leading cause of trial failure and regulatory rejection. Although MCP-Mod is widely adopted and endorsed by regulatory agencies, it requires prespecification of candidate models and is highly sensitive to model misspecification. To address these challenges, we introduce MAP-curvature, a general model-free framework for dose-response modelling that penalises the t…

working for a large corporation sometimes reminds me of the GDR. We had western TV and thus knew what's technically possible. Yet we didn't had the latest tech available or there were restrictions to use certain tech. Trying to talk to Atlassian Cloud with an MCP server that by default runs inside a Docker container is such a problem. Theoretically easy, practically a whole lot of workarounds required. Can't use Docker Desktop, Apple Containers would start, but the connection to …

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Yaxin Du, Yuanshuo Zhang, Xiyuan Yang, Yifan Zhou, Cheng Wang, Gongyi Zou, Xianghe Pang, Wenhao Wang, Menglan Chen, Shuo Tang, Zhiyu Li, Siheng Chen
https://arxiv.org/abs/2510.02271

InfoMosaic-Bench: Evaluating Multi-Source Information Seeking in Tool-Augmented Agents
Information seeking is a fundamental requirement for humans. However, existing LLM agents rely heavily on open-web search, which exposes two fundamental weaknesses: online content is noisy and unreliable, and many real-world tasks require precise, domain-specific knowledge unavailable from the web. The emergence of the Model Context Protocol (MCP) now allows agents to interface with thousands of specialized tools, seemingly resolving this limitation. Yet it remains unclear whether agents can ef…

📊 Multiple #MCP servers can be connected in single request, enabling #AI coordination across different systems for complex business workflows and automation
🌐

Google launches the Data Commons MCP Server, allowing developers to integrate its collection of public datasets into AI systems via natural language queries (Jagmeet Singh/TechCrunch)
https://techcrunch.com/2025/09/24/goog

Google makes real-world data more accessible to AI — and training pipelines will love it | TechCrunch
Google’s Data Commons gets an MCP Server to help AI systems access massive amounts of real-world data.

Crosslisted article(s) found for cs.IR. https://arxiv.org/list/cs.IR/new
[1/1]:
- Dynamic ReAct: Scalable Tool Selection for Large-Scale MCP Environments
Nishant Gaurav, Adit Akarsh, Ankit Ranjan, Manoj Bajaj

PentestMCP: A Toolkit for Agentic Penetration Testing
Zachary Ezetta, Wu-chang Feng
https://arxiv.org/abs/2510.03610 https://arxiv.org/pdf/2510.03610

PentestMCP: A Toolkit for Agentic Penetration Testing
Agentic AI is transforming security by automating many tasks being performed manually. While initial agentic approaches employed a monolithic architecture, the Model-Context-Protocol has now enabled a remote-procedure call (RPC) paradigm to agentic applications, allowing for the flexible construction and composition of multi-function agents. This paper describes PentestMCP, a library of MCP server implementations that support agentic penetration testing. By supporting common penetration testing…

🤖 #CodexSubagentsMCP creates file-based sub-agents for #CodexCLI via a minimal #MCP server with just one tool and maximum auditability

Anthropic's Skills for Claude, which are conceptually very simple, may become a bigger deal than MCP, whose high token usage is its most significant limitation (Simon Willison/Simon Willison's Weblog)
https://simonwillison.net/2025/Oct/16/claude-skills/

Claude Skills are awesome, maybe a bigger deal than MCP
Anthropic this morning introduced Claude Skills, a new pattern for making new abilities available to their models: Claude can now use Skills to improve how it performs specific tasks. Skills …

🗺️ 🚀 If you plan your next vacation trip, you have to check this out ‼️
This #MCP saved me days of planning! NO JOKE 🤯
👇 #AI #travel

AI Agents with Human-Like Collaborative Tools: Adaptive Strategies for Enhanced Problem-Solving
Harper Reed, Michael Sugimura, Angelo Zangari
https://arxiv.org/abs/2509.13547 ht…

AI Agents with Human-Like Collaborative Tools: Adaptive Strategies for Enhanced Problem-Solving
We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and allow them to use these tools as they see fit. Across 34 Aider Polyglot Python programming challenges, collaborative tools substantially improve performance on the hardest problems, delivering 15-40% lower cost, 12-27% fewer turns, and 12-38% faster completion th…

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
Ping He, Changjiang Li, Binbin Zhao, Tianyu Du, Shouling Ji
https://arxiv.org/abs/2509.21011 https://

Automatic Red Teaming LLM-based Agents with Model Context Protocol Tools
The remarkable capability of large language models (LLMs) has led to the wide application of LLM-based agents in various domains. To standardize interactions between LLM-based agents and their environments, model context protocol (MCP) tools have become the de facto standard and are now widely integrated into these agents. However, the incorporation of MCP tools introduces the risk of tool poisoning attacks, which can manipulate the behavior of LLM-based agents. Although previous studies have i…

GitHub updates VS Code with Plan Mode for building step-by-step project approaches, MCP Registry integration, definable project rules via AGENTS.md, and more (Sean Michael Kerner/VentureBeat)
https://venturebeat.com/ai/githubs-agent-hq-aims…

📊 Automated performance audits - run performance traces, analyze results, and investigate specific issues like high #LCP numbers for faster loading
⚙️ Easy setup with single #MCP client config entry using #npx

🛡️ Enterprise-grade security with proper authentication handling, structured responses containing tool discovery, reasoning steps, and execution results
💰 Simple pricing model - pay only for tokens consumed by selected #GroqCloud model, bring your own #MCP server and API key with third-par…

Toward PDDL Planning Copilot
Yarin Benyamin, Argaman Mordoch, Shahaf S. Shperberg, Roni Stern
https://arxiv.org/abs/2509.12987 https://arxiv.org/pdf/2509.1…

Toward PDDL Planning Copilot
Large Language Models (LLMs) are increasingly being used as autonomous agents capable of performing complicated tasks. However, they lack the ability to perform reliable long-horizon planning on their own. This paper bridges this gap by introducing the Planning Copilot, a chatbot that integrates multiple planning tools and allows users to invoke them through instructions in natural language. The Planning Copilot leverages the Model Context Protocol (MCP), a recently developed standard for conne…

Replaced article(s) found for physics.ins-det. https://arxiv.org/list/physics.ins-det/new
[1/1]:
- First experimental proof of PET imaging based on multi-anode MCP-PMTs with Cherenkov radiator-int...
Weiyan Pan, et al.

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
Shouju Wang, Fenglin Yu, Xirui Liu, Xiaoting Qin, Jue Zhang, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan
https://arxiv.org/abs/2509.17488

Privacy in Action: Towards Realistic Privacy Mitigation and Evaluation for LLM-Powered Agents
The increasing autonomy of LLM agents in handling sensitive communications, accelerated by Model Context Protocol (MCP) and Agent-to-Agent (A2A) frameworks, creates urgent privacy challenges. While recent work reveals significant gaps between LLMs' privacy Q&A performance and their agent behavior, existing benchmarks remain limited to static, simplified scenarios. We present PrivacyChecker, a model-agnostic, contextual integrity based mitigation approach that effectively reduces privacy leakage…

Avoid polluted areas with live air quality insights, ideal for healthier urban driving.
📍 Multi-Location Search
Find combined destinations like “gas station café” in a single API call for efficient break planning.
🔗 Get Started, Thank me later: https://github.com/Garblesnarff/google

people get creative when it comes to saving tokens.... 👀
#ai

Give you #AI some intelligent #memory with #graphiti #MCP 🤖🚀📝
i made a fork with some nice feat…

🚀 #Groq launches remote #MCP support in beta on #GroqCloud - connecting #AI models to external tools …

🚀 #Chrome #DevTools launches #MCP server in public preview - revolutionizing #AI coding assistants by…